Passenger docking location selection

Patent metadata

Field	Value
Publication number	US-9625906-B2
Application number	US-201514597568-A
Country	US
Kind code	B2
Filing date	Jan 15, 2015
Priority date	Jan 15, 2015
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

A method and apparatus for passenger docking location selection are disclosed. Passenger docking location selection may include an autonomous vehicle identifying transportation network information representing a vehicle transportation network, the vehicle transportation network including a primary destination, wherein identifying the transportation network information includes identifying the transportation network information such that it includes docking location information representing a plurality of docking locations, wherein each docking location corresponds with a respective location in the vehicle transportation network, and such that at least one docking location is associated with the primary destination, determining a target docking location for the primary destination based on the transportation network information and pedestrian travel time, identifying a first route from an origin to the target docking location in the vehicle transportation network using the transportation network information, and traveling from the origin to the target docking location using the first route.

First claim

What is claimed is:

1. An autonomous vehicle comprising:
a processor configured to execute instructions stored on a non-transitory computer readable medium to:
identify transportation network information representing a vehicle transportation network, the vehicle transportation network including a primary destination, wherein identifying the transportation network information includes identifying the transportation network information such that the transportation network information includes docking location information representing a plurality of docking locations, wherein each docking location from the plurality of docking locations corresponds with a respective location in the vehicle transportation network, and such that at least one docking location from the plurality of docking locations is associated with the primary destination, and such that the transportation network information indicates a set of candidate docking locations from the plurality of docking locations wherein each candidate docking location from the set of candidate docking locations is associated with the primary destination, and such that the transportation network information includes pedestrian transportation network information representing a pedestrian transportation network such that each candidate docking location from the set of candidate docking locations is proximal to a respective portion of the pedestrian transportation network;
determine a target docking location from the plurality of docking locations for the primary destination based on the transportation network information and pedestrian travel time by selecting the target docking location from the plurality of candidate docking locations based on pedestrian travel time between the target docking location and the primary destination, wherein selecting the target docking location from the plurality of candidate docking locations includes generating a pedestrian decision model that indicates a plurality of candidate paths between the primary destination and each respective candidate docking location from the plurality of candidate docking locations; and
identify a first route from an origin to the target docking location in the vehicle transportation network using the transportation network information; and

a trajectory controller configured to operate the autonomous vehicle in accordance with the first route such that the autonomous vehicle traverses the vehicle transportation network from the origin to the target docking location.

2. The autonomous vehicle of claim 1 , wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:
in response to performing a docking operation at the target docking location, identify a secondary destination in the vehicle transportation network, wherein the secondary destination is a parking area associated with the primary destination, and wherein the trajectory controller is configured to operate the autonomous vehicle to park at the secondary destination;
identify a second route from the target docking location to the secondary destination in the vehicle transportation network using the transportation network information, and wherein the trajectory controller is configured to operate the autonomous vehicle in accordance with the second route such that the autonomous vehicle traverses the vehicle transportation network from the target docking location to the secondary destination.

3. The autonomous vehicle of claim 2 , wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:
identify a second target docking location associated with the primary destination; and
generate a pedestrian travel route between the target docking location and the second target docking location.

4. The autonomous vehicle of claim 3 , wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:
identify a third route from the secondary destination to the second target docking location in the vehicle transportation network using the transportation network information, and wherein the trajectory controller is configured to operate the autonomous vehicle in accordance with the third route such that the autonomous vehicle traverses the vehicle transportation network from the secondary destination to the second target docking location.

5. The autonomous vehicle of claim 1 , wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to identify the transportation network information such that the docking location information is based on operating information for a plurality of vehicles, wherein the operating information includes a plurality of operations, wherein each operation from the plurality of operations is associated with a respective vehicle from the plurality of vehicles, and wherein each docking location from the plurality of docking locations corresponds with a respective operation from the plurality of operations.

6. The autonomous vehicle of claim 1 , wherein determining the target docking location includes receiving user input indicating an entrance location for the primary destination and using the entrance location as the primary destination.

7. The autonomous vehicle of claim 1 , wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to identify the transportation network information such that a portion of the pedestrian transportation network is proximal to the primary destination.

8. The autonomous vehicle of claim 1 , wherein determining the target docking location includes omitting a candidate docking location from the plurality of candidate docking locations on a condition that a predicted pedestrian travel time between the candidate docking location and the primary destination exceeds a maximum pedestrian travel time.

9. The autonomous vehicle of claim 1 , wherein the pedestrian decision model includes a plurality of routing states, wherein each candidate docking location from the plurality of candidate docking locations corresponds with a respective routing state.

10. The autonomous vehicle of claim 9 , wherein generating the pedestrian decision model includes generating a plurality of predicted costs, wherein each predicted cost from the plurality of predicted cots represents a predicted pedestrian travel time between the primary destination and a respective routing state from the plurality of routing states.

11. The autonomous vehicle of claim 10 , wherein determining the target docking location includes determining a minimal travel time that includes a sum of a predicted travel time between the origin and the target docking location and a predicted pedestrian travel time between the target docking location and the primary destination.

12. The autonomous vehicle of claim 10 , wherein determining the target docking location includes:
generating a vehicle decision model that indicates a plurality of candidate paths between the origin and each respective candidate docking location from the plurality of candidate docking locations; and
generating an augmented decision model based on the pedestrian decision model and the vehicle decision model.

13. The autonomous vehicle of claim 12 , wherein generating the augmented decision model includes generating the augmented decision model such that an action cost associated with using a candidate docking location as the target docking location includes the predicted pedestrian travel time between the target docking location and the primary location and a defined docking oper

Assignees

• Nissan North America Inc

Inventors

• Meuleau Nicolas
• Thakur Siddharth Kumar
• Kojo Naoki
• Saito Daisuke
• Lele Nikhil

Classifications

• G08G1/00

  Traffic control systems for road vehicles (arrangement of road signs or traffic signals E01F9/00 {; automatic vehicle control B62D}) · CPC title

• G01C21/3407 Primary

  specially adapted for specific applications · CPC title

• G05D1/0088 Primary

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G06Q10/047

  Optimisation of routes or paths, e.g. travelling salesman problem · CPC title

• G08G1/146

  where the parking area is a limited parking space, e.g. parking garage, restricted space · CPC title